Uploaded image for project: 'Hadoop Map/Reduce'
  1. Hadoop Map/Reduce
  2. MAPREDUCE-4305

Implement delay scheduling in capacity scheduler for improving data locality

    XMLWordPrintableJSON

Details

    • New Feature
    • Status: Open
    • Major
    • Resolution: Unresolved
    • None
    • None
    • None
    • None

    Description

      Capacity Scheduler data local tasks are about 40%-50% which is not good.
      While my test with 70 node cluster i consistently get data locality around 40-50% on a free cluster.

      I think we need to implement something like delay scheduling in the capacity scheduler for improving the data locality.
      http://radlab.cs.berkeley.edu/publication/308

      After implementing the delay scheduling on Hadoop 22 I am getting 100 % data locality in free cluster and around 90% data locality in busy cluster.

      Thanks,
      Mayank

      Attachments

        1. PATCH-MAPREDUCE-4305-MR1-7.patch
          35 kB
          Mayank Bansal
        2. PATCH-MAPREDUCE-4305-MR1-6.patch
          35 kB
          Mayank Bansal
        3. PATCH-MAPREDUCE-4305-MR1-3.patch
          40 kB
          Mayank Bansal
        4. PATCH-MAPREDUCE-4305-MR1-2.patch
          39 kB
          Mayank Bansal
        5. PATCH-MAPREDUCE-4305-MR1-1.patch
          43 kB
          Mayank Bansal
        6. PATCH-MAPREDUCE-4305-MR1.patch
          43 kB
          Mayank Bansal
        7. MAPREDUCE-4305-1.patch
          22 kB
          Mayank Bansal
        8. MAPREDUCE-4305
          22 kB
          Mayank Bansal

        Issue Links

          Activity

            People

              mayank_bansal Mayank Bansal
              mayank_bansal Mayank Bansal
              Votes:
              0 Vote for this issue
              Watchers:
              22 Start watching this issue

              Dates

                Created:
                Updated: